Tourist reviews provide essential insights into travellers experiences and public perceptions of destinations. In Kazakhstan, however, sentiment analysis, particularly using ensemble learning, remains underexplored for evaluating such reviews. This study proposes a hybrid stacking ensemble for sentiment analysis of English-language tourist reviews about Kazakhstan, integrating four complementary approaches: VADER, TextBlob, Stanza, and Local Context Focus Mechanism with Bidirectional Encoder Representations from Transformers (LCF-BERT). Each model contributes distinct analytical capabilities, including lexicon-based polarity detection, rule-based subjectivity evaluation, generalised star-rating estimation, and contextual aspect-oriented sentiment classification. The evaluation utilised a cleaned dataset of 11,454 TripAdvisor reviews collected between February 2022 and June 2025. The ensemble aggregates model outputs through majority and weighted voting strategies to enhance robustness. Experimental results (accuracy 0.891, precision 0.838, recall 0.891, and F1-score 0.852) demonstrate that the proposed method KazSATR outperforms individual models in overall classification accuracy and exhibits superior capacity for aspect-level sentiment detection. These findings underscore the potential of the hybrid ensemble as a practical and scalable tool for the tourism sector in Kazakhstan. By leveraging multiple analytical paradigms, the model enables tourism professionals and policymakers to better understand traveller preferences, identify service strengths and weaknesses, and inform strategic decision-making. The proposed approach contributes to advancing sentiment analysis applications in tourism research, particularly in underrepresented geographic contexts.
This paper reports a systematic study of low-rank adaptation (LoRA)-based fine-tuning applied to Qwen3 language models (4B, 8B, and 14B parameters) for the task of legal question answering within the jurisdiction of the Republic of Kazakhstan. The bilingual dataset comprises 63,114 question–answer pairs (76.2% Russian, 23.8% Kazakh) covering 11 legal domains. Models are evaluated through both automated metrics (BERTScore, citation accuracy, and hallucination rate) and blind expert assessment by a panel of two practising legal experts. Key findings: (1) all fine-tuned models reach BERTScore F1 close to 90% (89.6–90.2%) versus 82.2–83.1% for untuned base models; (2) fine-tuned models outperform GPT-4o (87.2%) and GPT-4o-mini (86.7%) on semantic similarity while exhibiting far lower hallucination rates (27–29% vs. 83–90%); (3) blind expert assessment confirms the advantage of fine-tuned models, with panel mean completeness scores of 4.28/5 versus 1.95/5 for base models (quadratically weighted Cohen’s κ = 0.80–0.95 across rating dimensions, indicating substantial to almost perfect inter-rater agreement); and (4) we identify a practical scaling plateau: paired Wilcoxon tests (n = 500) detect statistically significant but practically small differences across the 4B, 8B, and 14B fine-tuned variants (largest mean gap 0.67 pp on BERTScore F1; Cohen’s |d_z| ≤ 0.34), gains too small to justify the 3.5× parameter increase. These findings show that parameter-efficient adaptation of compact open-source models can match or exceed commercial LLMs for specialised legal QA in a low-resource bilingual context. We note one scope restriction: three domains (administrative, criminal, and housing law) are represented only in Russian, so the model is not validated for Kazakh language queries in these areas.
Fine-grained analysis of guest satisfaction in the hospitality sector requires moving beyond document-level sentiment classification. It calls for structured extraction of attribute-specific evaluations from multilingual user-generated content. However, existing approaches have yet to address this methodological gap for the Central Asian hotel market. This study presents KAZ-LLM-ABSA, a generative framework for Aspect Sentiment Triplet Extraction applied to trilingual hotel reviews (Kazakh, English, and Russian) in Kazakhstan. The framework fine-tunes Qwen2.5-7B-Instruct via QLoRA on a purpose-built gold standard of 1726 expert-annotated triplets, formulating ASTE as an end-to-end sequence-to-sequence task to eliminate error propagation inherent to pipeline architectures. Benchmarked against six baselines spanning discriminative encoder models (mBERT-base, XLM-RoBERTa-base, BERT-SPC, LCF-BERT, RoBERTa-large) and a generative Seq2Seq model (GAS-mT5-base). KAZ-LLM-ABSA outperforms existing models across the reported metrics, demonstrating superior performance on the trilingual Kazakhstan hotel review corpus. These findings confirm the transferability of fine-tuned LLMs to low-resource multilingual hospitality data and offer practitioners a structured tool for aspect-level service quality diagnostics.
The digital transformation of tourism has turned traveler reviews into a continuously expanding record of what visitors value, yet this evidence is fragmented across platforms and languages and is usually reduced to star ratings that obscure the underlying structure of preferences. This study develops a method for the aspect-based semantic analysis of tourist preferences and applies it to Kazakhstan, an emerging destination whose digital space spans three languages. We assembled a corpus of 571,153 reviews from 2GIS, Booking, TripAdvisor, and GetYourGuide in Russian, Kazakh, and English, balanced it to 234,663 reviews, and annotated a gold set of 1500 reviews against an 11-aspect taxonomy. Aspect categories were detected with a linear support vector model, and their sentiment was classified with a multilingual transformer, enabling reliable processing of short, code-mixed texts. The results show that platforms do not merely differ in tone but describe fundamentally different destinations. 2GIS, which carries the domestic voice, diverges sharply from the international platforms, whereas TripAdvisor and GetYourGuide are almost indistinguishable. Domestic and inbound tourists likewise emphasize different aspects, with food and service dominating domestic reviews and location, infrastructure, and nature dominating inbound ones. These findings demonstrate that any single-source analysis yields a systematically biased picture of a destination and argue for multilingual, multi-platform designs in tourism analytics.
Kazakh Sign Language (KSL) has received little attention in automatic sign language recognition. Its fingerspelling alphabet contains 44 signs (42 letters and two function signs), and 12 of the letters (28.6%) involve hand movement in addition to handshape. This paper presents QazSL, a dataset covering all 44 classes, with 110,000 labelled video recordings (about 2500 per class, red–green–blue (RGB), 640 × 480) made by five native signers. An optimal-frame selection module extracted one 50 × 50 greyscale image per recording, which defines a deliberately simplified single-frame classification task: letters with movement are recognised from the handshape held during the sign, not from their movement. Eight architectures were compared under identical training conditions, from a baseline convolutional neural network (CNN) to attention-based, recurrent and multi-scale Inception models with residual connections. The proposed Inception Hybrid model (2.85 million parameters) achieves 98.49% accuracy on a validation split that shares signers with the training data and 97.41% on an independent test set of five new signers, in single training runs. All 44 classes are recognised with at least 95% accuracy; the lowest values are obtained for letters with movement, which are most often confused with static letters of similar handshape, showing the limits of the single-frame approach. On a consumer laptop, inference takes about 1.5 ms per frame on the graphics processing unit (GPU) and 41–43 ms on one thread of the central processing unit (CPU). Only an ordinary webcam is needed, which makes the system a promising basis for assistive fingerspelling input.